taoyunuo

求助~~~如何获得测试数据 分类为某一个标签得概率或者得分呢？

2

训练好的模型直接拿来测试，给数据后直接输出判断结果，如何得出 它分到这个类别得概率呢? 谢谢

loss is about 9？？How to make loss drop

7

my solver ： base_lr: 0.01 lr_policy: "multistep" gamma: 0.1 stepvalue: 16000 stepvalue: 24000 stepvalue: 28000 max_iter: 28000 display: 100 momentum: 0.9 weight_decay: 0.0005 #snapshot: 1000 snapshot_prefix: "result/sphereface_model_old"

What is the maximum number of iterations?

4

I can not understand how to set the max-iterations in the code, Please help me to understand,thanks

为什么 test的时候，预测结果都是同一个标签？

4

我训练的时候 一共7个 lable 每个lable在训练集的样本数量都是5000，可以训练好进行模型测试的时候，测试出来的标签都是同一个label（比如全是 手机）

label_specific_add error

3

src/caffe/layers/label_specific_add.cpp:28:7: error: converting to ‘const std::vector’ from initializer list would use explicit constructor ‘std::vector::vector(std::vector::size_type, const value_type&, const allocator_type&) [with _Tp = int; _Alloc = std::allocator; std::vector::size_type = long unsigned int;...

How to test the model use LFW?

4

Please provide specific test methods，thanks！